AI Paper Atlas

Research map / Benchmarks / WiC

WiC leaderboard

22 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on WiC. Best accuracy: 72.1 (RoBERTa-large + SemPre, AAAI 2021).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

WiC · accuracy

22 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
172.1RoBERTa-large + SemPre
RoBERTa-large
Towards Semantics-Enhanced Pre-Training: Can Lexicon Definitions Help Learning Sentence Meanings?
AAAI 2021 · Table 3
Language, safety and interpretability
270.8FedSEA-LLaMA
LLaMA2-7B
FedSEA-LLaMA: A Secure, Efficient and Adaptive Federated Splitting Framework for Large Language Models
AAAI 2026 · Table 1
Privacy attacks and secure learning
367.8AGZO
Qwen3-4B
AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
ICML 2026 · Table 2
Pruning and efficient tuning
466.18DLF
DistilRoBERTa
Knowledge Distillation of Uncertainty using Deep Latent Factor Model
NeurIPS 2025 · Results on GLUE and SuperGLUE
Uncertainty and Gaussian processes
565.4LoHO-Adaminter
OPT-13B
Towards Efficient Low-Order Hybrid Optimizer for Language Model Fine-Tuning
AAAI 2025 · Table 2
Pruning and efficient tuning
664.9LOZO+ (greedy)
OPT-13B
LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace Selection
ICML 2026 · Table 5
Optimizers
764.9S-MeZO
LLaMA-7b
Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
NeurIPS 2025 · Table: Accuracy of Fine-Tuning
Pruning and efficient tuning
864.4Hybrid-Prompt
Llama-2-7b
New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework
ICLR 2026 · Table 1
Instruction and fine-tuning
964.16GEM
OPT-125M
GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation
AAAI 2026 · Table 3
Pruning and efficient tuning
1063.3BC
PaLM 2-S
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
ICLR 2024 · Table: Accuracy on natural lan
Language, safety and interpretability
12 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.